ICLR

Efficient Model-Based Reinforcement Learning Through Optimistic Thompson Sampling

Jasmine Bayrooti, Carl Henrik Ek, Amanda Prorok

Comments Appearing in ICLR, 2025

Task-Adaptive Pretrained Language Models via Clustered-Importance Sampling

David Grangier, Simin Fan, Skyler Seto, Pierre Ablin

Comments 23 pages, presented at the International Conference on Learning Representation (ICLR), 2025

Agent-Oriented Planning in Multi-Agent Systems

Ao Li, Yuexiang Xie, Songze Li, Fugee Tsung, Bolin Ding, Yaliang Li

Comments Accepted by ICLR'2025

Breaking Neural Network Scaling Laws with Modularity

Akhilan Boopathy, Sunshine Jiang, William Yue, Jaedong Hwang, Abhiram Iyer, Ila Fiete

Comments ICLR 2025

Visual Haystacks: A Vision-Centric Needle-In-A-Haystack Benchmark

Tsung-Han Wu, Giscard Biamby, Jerome Quenum, Ritwik Gupta, Joseph E. Gonzalez, Trevor Darrell, David M. Chan

Comments Accepted to ICLR 2025; Project page: https://visual-haystacks.github.io

Learning local equivariant representations for quantum operators

Zhanghao Zhouyin, Zixi Gan, MingKang Liu, Shishir Kumar Pandey, Linfeng Zhang, Qiangqiang Gu

Comments 11 pages, 5 figures and 5 tables

Journal ref International Conference on Learning Representations (ICLR), 2025

AdaFisher: Adaptive Second Order Optimization via Fisher Information

Damien Martins Gomes, Yanlei Zhang, Eugene Belilovsky, Guy Wolf, Mahdi S. Hosseini

Comments Accepted in ICLR 2025

Does SGD really happen in tiny subspaces?

Minhak Song, Kwangjun Ahn, Chulhee Yun

Comments Published at ICLR 2025

Standard Gaussian Process is All You Need for High-Dimensional Bayesian Optimization

Zhitong Xu, Haitao Wang, Jeff M Phillips, Shandian Zhe

Comments ICLR 2025 camera-ready version

Regularization by Texts for Latent Diffusion Inverse Solvers

Jeongsol Kim, Geon Yeong Park, Hyungjin Chung, Jong Chul Ye

Comments ICLR 2025 (Spotlight)

Should VLMs be Pre-trained with Image Data?

Sedrick Keh, Jean Mercat, Samir Yitzhak Gadre, Kushal Arora, Igor Vasiljevic, Benjamin Burchfiel, Shuran Song, Russ Tedrake, Thomas Kollar, Ludwig Schmidt, Achal Dave

Comments ICLR 2025

Improving Pretraining Data Using Perplexity Correlations

Tristan Thrush, Christopher Potts, Tatsunori Hashimoto

Comments ICLR 2025

Group-robust Sample Reweighting for Subpopulation Shifts via Influence Functions

Rui Qiao, Zhaoxuan Wu, Jingtan Wang, Pang Wei Koh, Bryan Kian Hsiang Low

Comments Accepted to the 13th International Conference on Learning Representations (ICLR 2025). Code is available at https://github.com/qiaoruiyt/GSR

When Selection Meets Intervention: Additional Complexities in Causal Discovery

Haoyue Dai, Ignavier Ng, Jianle Sun, Zeyu Tang, Gongxu Luo, Xinshuai Dong, Peter Spirtes, Kun Zhang

Comments Appears at ICLR 2025 (oral)

Journal ref Proceedings of the International Conference on Learning Representations (ICLR), 2025

PIED: Physics-Informed Experimental Design for Inverse Problems

Apivich Hemachandra, Gregory Kang Ruey Lau, See-Kiong Ng, Bryan Kian Hsiang Low

Comments Accepted to 13th International Conference on Learning Representations (ICLR 2025), 31 pages

Large Language Models Often Say One Thing and Do Another

Ruoxi Xu, Hongyu Lin, Xianpei Han, Jia Zheng, Weixiang Zhou, Le Sun, Yingfei Sun

Comments Published on ICLR 2025

Privacy Auditing of Large Language Models

Ashwinee Panda, Xinyu Tang, Milad Nasr, Christopher A. Choquette-Choo, Prateek Mittal

Comments ICLR 2025

Exploring LLM Agents for Cleaning Tabular Machine Learning Datasets

Tommaso Bendinelli, Artur Dox, Christian Holz

Comments 14 pages, 1 main figure, 3 plots, Published at ICLR 2025 Workshop on Foundation Models in the Wild

BingoGuard: LLM Content Moderation Tools with Risk Levels

Fan Yin, Philippe Laban, Xiangyu Peng, Yilun Zhou, Yixin Mao, Vaibhav Vats, Linnea Ross, Divyansh Agarwal, Caiming Xiong, Chien-Sheng Wu

Comments 10 pages, 4 figures, 4 tables. ICLR 2025 poster

IDInit: A Universal and Stable Initialization Method for Neural Network Training

Yu Pan, Chaozheng Wang, Zekai Wu, Qifan Wang, Min Zhang, Zenglin Xu

Comments Accepted in ICLR 2025

Self-Supervised Diffusion MRI Denoising via Iterative and Stable Refinement

Chenxu Wu, Qingpeng Kong, Zihang Jiang, S. Kevin Zhou

Comments 40pages, 34figures

Journal ref ICLR 2025

Explain-Query-Test: Self-Evaluating LLMs Via Explanation and Comprehension Discrepancy

Saeid Asgari Taghanaki, Joao Monteiro

Comments Accepted to ICLR 2025, SSI-FM

IVE: Enhanced Probabilistic Forecasting of Intraday Volume Ratio with Transformers

Hanwool Lee, Heehwan Park

Comments Accepted at FinancialAI@ICLR 2025

SplatFormer: Point Transformer for Robust 3D Gaussian Splatting

Yutong Chen, Marko Mihajlovic, Xiyi Chen, Yiming Wang, Sergey Prokudin, Siyu Tang

Comments ICLR 2025

CycleResearcher: Improving Automated Research via Automated Review

Yixuan Weng, Minjun Zhu, Guangsheng Bao, Hongbo Zhang, Jindong Wang, Yue Zhang, Linyi Yang

Comments Accept in ICLR 2025

Solving Differential Equations with Constrained Learning

Viggo Moro, Luiz F. O. Chamon

Comments ICLR 2025

ClimaQA: An Automated Evaluation Framework for Climate Question Answering Models

Veeramakali Vignesh Manivannan, Yasaman Jafari, Srikar Eranky, Spencer Ho, Rose Yu, Duncan Watson-Parris, Yian Ma, Leon Bergen, Taylor Berg-Kirkpatrick

Comments Accepted to ICLR 2025

Journal ref ICLR 2025

Hierarchical Uncertainty Estimation for Learning-based Registration in Neuroimaging

Xiaoling Hu, Karthik Gopinath, Peirong Liu, Malte Hoffmann, Koen Van Leemput, Oula Puonti, Juan Eugenio Iglesias

Comments 17 pages, 6 figures. Accepted by ICLR'25

FLOPS: Forward Learning with OPtimal Sampling

Tao Ren, Zishi Zhang, Jinyang Jiang, Guanghao Li, Zeliang Zhang, Mingqian Feng, Yijie Peng

Comments Published in the Thirteenth International Conference on Learning Representations(ICLR 2025)

SGD with memory: fundamental properties and stochastic acceleration

Dmitry Yarotsky, Maksim Velikanov

Comments ICLR 2025 camera ready